Alex Cristia (CNRS) “Diarization in the Wild: Challenges and Opportunities”

When:
April 22, 2019 @ 12:00 pm – 1:15 pm
2019-04-22T12:00:00-04:00
2019-04-22T13:15:00-04:00
Where:
Hackerman Hall B17
3400 N Charles St
Baltimore, MD 21218
USA

Abstract

Devices that document daily life experiences are now smarter, affordable, lightweight, easy to use, and able to record for a whole day. Daylong recordings from wearables could provide a unique view on the user’s spontaneous speech use, with no effort on their part. The long time scale facilitates habituation, and should lead to more ecological measures. Finally, the massive amount of data collected facilitates the study of intra- and inter-individual differences. These features are particularly important for a range of theoretical and applied questions building on spontaneous language use such as: What kinds of spoken interactions impact early language acquisition – and which improve seniors’ well-being? Is that child developing normally? Is that patient recovering or deteriorating? Is that intervention increasing social language use? In the present talk, I discuss the unique (technical, but also ethical, and legal) opportunities and challenges that such recordings offer, with a special accent on (automatic labeling of events (diarization).

Biography

After my BA in Letters at Universidad Nacional de Rosario (Argentina), a PhD in Linguistics at Purdue University, and a postdoctoral fellowship on neurobiology of language at the Max Planck Institute for Psycholinguistics (Netherlands), I became a Researcher with the CNRS in 2013, and joined my current lab, the LSCP (cofunded by EHESS, ENS, PSL University). In my work, I seek to answer the following questions: What are the linguistic representations that infants and adults have? Why and how are they formed? How may learnability biases shape the world’s languages? To answer these questions, I combine multiple methodologies including spoken corpora analyses, behavioral studies, neuroimaging (NIRS), computational modeling.

 

Johns Hopkins University

Johns Hopkins University, Whiting School of Engineering

Center for Language and Speech Processing
Hackerman 226
3400 North Charles Street, Baltimore, MD 21218-2680

Center for Language and Speech Processing